Accelerated serverless computing based on GPU virtualization

Naranjo, Diana; Risco, Sebastián; Alfonso, Carlos; Pérez, Alfonso García; Blanquer, Ignácio; Moltó, Germán

doi:10.1016/j.jpdc.2020.01.004

Cited by 39 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was precisely to avoid this overload that the second variant of packaging all the processing in a single function was selected. Source: [96] Several executions were implemented using the on-premises serverless platform, to analyze the total processing time in each of the proposed scenarios. In the executions, videos with different lengths were used, which could be decomposed into 60, 120, 180, 240, 300 and 360 frames.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…One of the limitations of using NVIDIA-Docker is that it restricts the use of the GPU concurrently by another container. Source: [96] As explained previously, the proposed architecture is based on the OSCAR framework that allows developers to run applications packaged in Docker containers as functions that are triggered in response to certain events, in this case when uploading a file to the MinIO input bucket. This event-based architecture simplifies data and infrastructure management by abstracting all end-user configurations [96].…”

Section: Nvidia Container Runtime For Dockermentioning

confidence: 99%

“…Source: [96] As explained previously, the proposed architecture is based on the OSCAR framework that allows developers to run applications packaged in Docker containers as functions that are triggered in response to certain events, in this case when uploading a file to the MinIO input bucket. This event-based architecture simplifies data and infrastructure management by abstracting all end-user configurations [96]. On the one hand, there is a Kuberentes cluster with the OSCAR framework that supports the implementation and execution of functions that run as Kubernetes jobs.…”

Section: Nvidia Container Runtime For Dockermentioning

confidence: 99%

“…Once OSCAR Manager receives the request for a new function, Kaniko is executed, where in addition to the user's application, Figure 4.3: Integration of rCUDA into the OSCAR architecture. Source: [96] the rCUDA client libraries and the environment variables required for the configuration, such as the IP of the server and the number of GPUs to be used, are included in the construction of the image. This is executed as Kubernetes jobs and the communication with the server is through the network.…”

Section: Architecturementioning

confidence: 99%

“…This serverless execution strategy allows optimizing the use of GPUs, as well as reducing the cost of implementation, since rCUDA allows the use of a GPU by multiple applications. This architecture extends the support of the OSCAR serverless platform into mixed workloads that include standard CPU and GPU requirements [96].…”

Section: Architecturementioning

confidence: 99%

See 4 more Smart Citations

Serverless Computing Strategies on Cloud Platforms

Delgado¹,

María²

View full text Add to dashboard Cite

First of all I want to thank my parents for always being there for me and supporting me in all the decisions I have made throughout my life. To my sister, who is my role model, for encouraging me to embark on this completely new adventure for me. To my husband for always being by my side and making my days happy just by his presence. I would like to thank all my GRyCAP colleagues for their support throughout this thesis and my career in the research group. Especially all my gratitude to Ignacio Blanquer and Germán Moltó for trusting me from the first day and providing me with all the tools and help necessary for the development of this research. With all of you I will be eternally grateful. I want to express all my gratitude to all my friends who in one way or another have always supported and encouraged me in difficult moments. I would also like to thank all the people who have participated in my training as a person. Thanks to all of them I have been advancing in my life and I have reached this point. iii

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Section: Nvidia Container Runtime For Dockermentioning

confidence: 99%

Section: Nvidia Container Runtime For Dockermentioning

confidence: 99%

Section: Architecturementioning

confidence: 99%

Section: Architecturementioning

confidence: 99%

See 3 more Smart Citations

Serverless Computing Strategies on Cloud Platforms

Delgado¹,

María²

View full text Add to dashboard Cite

show abstract

A serverless gateway for event‐driven machine learning inference in multiple clouds

Naranjo

Risco

Moltó

et al. 2021

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Serverless computing and, in particular, the functions as a service model has become a convincing paradigm for the development and implementation of highly scalable applications in the cloud. This is due to the transparent management of three key functionalities: triggering of functions due to events, automatic provisioning and scalability of resources, and fine-grained pay-per-use. This article presents a serverless web-based scientific gateway to execute the inference phase of previously trained machine learning and artificial intelligence models. The execution of the models is performed both in Amazon Web Services and in on-premises clouds with the OSCAR framework for serverless scientific computing. In both cases, the computing infrastructure grows elastically according to the demand adopting scale-to-zero approaches to minimize costs.The web interface provides an improved user experience by simplifying the use of the models. The usage of machine learning in a computing platform that can use both on-premises clouds and public clouds constitutes a step forward in the adoption of serverless computing for scientific applications.

show abstract

Edge‐adaptable serverless acceleration for machine learning Internet of Things applications

2020

View full text Add to dashboard Cite

Serverless computing is an emerging event‐driven programming model that accelerates the development and deployment of scalable web services on cloud computing systems. Though widely integrated with the public cloud, serverless computing use is nascent for edge‐based, Internet of Things (IoT) deployments. In this work, we present STOIC (serverless teleoperable hybrid cloud), an IoT application deployment and offloading system that extends the serverless model in three ways. First, STOIC adopts a dynamic feedback control mechanism to precisely predict latency and dispatch workloads uniformly across edge and cloud systems using a distributed serverless framework. Second, STOIC leverages hardware acceleration (e.g., GPU resources) for serverless function execution when available from the underlying cloud system. Third, STOIC can be configured in multiple ways to overcome deployment variability associated with public cloud use. We overview the design and implementation of STOIC and empirically evaluate it using real‐world machine learning applications and multitier IoT deployments (edge and cloud). Specifically, we show that STOIC can be used for training image processing workloads (for object recognition)—once thought too resource‐intensive for edge deployments. We find that STOIC reduces overall execution time (response latency) and achieves placement accuracy that ranges from 92% to 97%.

show abstract

Accelerated serverless computing based on GPU virtualization

Cited by 39 publications

References 23 publications

Serverless Computing Strategies on Cloud Platforms

Serverless Computing Strategies on Cloud Platforms

A serverless gateway for event‐driven machine learning inference in multiple clouds

Edge‐adaptable serverless acceleration for machine learning Internet of Things applications

Contact Info

Product

Resources

About